Hospital Length of Stay and 30-Day Mortality Prediction in Stroke: A Machine Learning Analysis of 17,000 ICU Admissions in Brazil

Machine learning-based prognostication of mortality in stroke patients

Objectives

Predicting stroke mortality is crucial for personalized care. This study aims to design and evaluate a machine learning model to predict one-year mortality after a stroke.

Materials and methods

Data from the National Multiethnic Stroke Registry was utilized. Eight machine learning (ML) models were trained and evaluated using various metrics. SHapley Additive exPlanations (SHAP) analysis was used to identify the influential predictors.

Results

The final analysis included 9840 patients diagnosed with stroke were included in the study. The XGBoost algorithm exhibited optimal performance with high accuracy (94.5%) and AUC (87.3%). Core predictors encompassed National Institutes of Health Stroke Scale (NIHSS) at admission, age, hospital length of stay, mode of arrival, heart rate, and blood pressure. Increased NIHSS, age, and longer stay correlated with higher mortality. Ambulance arrival and lower diastolic blood pressure and lower body mass index predicted poorer outcomes.

Conclusions

This model's predictive capacity emphasizes the significance of NIHSS, age, hospital stay, arrival mode, heart rate, blood pressure, and BMI in stroke mortality prediction. Specific findings suggest avenues for data quality enhancement, registry expansion, and real-world validation. The study underscores machine learning's potential for early mortality prediction, improving risk assessment, and personalized care. The potential transformation of care delivery through robust ML predictive tools for Stroke outcomes could revolutionize patient care, allowing for personalized plans and improved preventive strategies for stroke patients. However, it is imperative to conduct prospective validation to evaluate its practical clinical effectiveness and ensure its successful adoption across various healthcare environments.

National ICU Registries as Enablers of Clinical Research and Quality Improvement

OBJECTIVES

Clinical quality registries (CQRs) have been implemented worldwide by several medical specialties aiming to generate a better characterization of epidemiology, treatments, and outcomes of patients. National ICU registries were created almost 3 decades ago to improve the understanding of case-mix, resource use, and outcomes of critically ill patients. This narrative review describes the challenges, proposed solutions, and evidence generated by National ICU registries as facilitators for research and quality improvement.

DATA SOURCES

English language articles were identified in PubMed using phrases related to ICU registries, CQRs, outcomes, and case-mix.

STUDY SELECTION

Original research, review articles, letters, and commentaries, were considered.

DATA EXTRACTION

Data from relevant literature were identified, reviewed, and integrated into a concise narrative review.

DATA SYNTHESIS

CQRs have been implemented worldwide by several medical specialties aiming to generate a better characterization of epidemiology, treatments, and outcomes of patients. National ICU registries were created almost 3 decades ago to improve the understanding of case-mix, resource use, and outcomes of critically ill patients. The initial experience in European countries and in Oceania ensured that through locally generated data, ICUs could assess their performances by using risk-adjusted measures and compare their results through fair and validated benchmarking metrics with other ICUs contributing to the CQR. The accomplishment of these initiatives, coupled with the increasing adoption of information technology, resulted in a broad geographic expansion of CQRs as well as their use in quality improvement studies, clinical trials as well as international comparisons, and benchmarking for ICUs.

CONCLUSIONS

ICU registries have provided increased knowledge of case-mix and outcomes of ICU patients based on real-world data and contributed to improve care delivery through quality improvement initiatives and trials. Recent increases in adoption of new technologies (i.e., cloud-based structures, artificial intelligence, machine learning) will ensure a broader and better use of data for epidemiology, healthcare policies, quality improvement, and clinical trials.

A clinical prediction model based on interpretable machine learning algorithms for prolonged hospital stay in acute ischemic stroke patients: a real-world study

Objective

Acute ischemic stroke (AIS) brings an increasingly heavier economic burden nowadays. Prolonged length of stay (LOS) is a vital factor in healthcare expenditures. The aim of this study was to predict prolonged LOS in AIS patients based on an interpretable machine learning algorithm.

Methods

We enrolled AIS patients in our hospital from August 2017 to July 2019, and divided them into the "prolonged LOS" group and the "no prolonged LOS" group. Prolonged LOS was defined as hospitalization for more than 7 days. The least absolute shrinkage and selection operator (LASSO) regression was applied to reduce the dimensionality of the data. We compared the predictive capacity of extended LOS in eight different machine learning algorithms. SHapley Additive exPlanations (SHAP) values were used to interpret the outcome, and the most optimal model was assessed by discrimination, calibration, and clinical utility.

Results

Prolonged LOS developed in 149 (22.0%) of the 677 eligible patients. In eight machine learning algorithms, prolonged LOS was best predicted by the Gaussian naive Bayes (GNB) model, which had a striking area under the curve (AUC) of 0.878 ± 0.007 in the training set and 0.857 ± 0.039 in the validation set. The variables sorted by the gap values showed that the strongest predictors were pneumonia, dysphagia, thrombectomy, and stroke severity. High net benefits were observed at 0%-76% threshold probabilities, while good agreement was found between the observed and predicted probabilities.

Conclusions

The model using the GNB algorithm proved excellent for predicting prolonged LOS in AIS patients. This simple model of prolonged hospitalization could help adjust policies and better utilize resources.

Risk factor identification and prediction models for prolonged length of stay in hospital after acute ischemic stroke using artificial neural networks

Background

Accurate estimation of prolonged length of hospital stay after acute ischemic stroke provides crucial information on medical expenditure and subsequent disposition. This study used artificial neural networks to identify risk factors and build prediction models for a prolonged length of stay based on parameters at the time of hospitalization.

Methods

We retrieved the medical records of patients who received acute ischemic stroke diagnoses and were treated at a stroke center between January 2016 and June 2020, and a retrospective analysis of these data was performed. Prolonged length of stay was defined as a hospital stay longer than the median number of days. We applied artificial neural networks to derive prediction models using parameters associated with the length of stay that was collected at admission, and a sensitivity analysis was performed to assess the effect of each predictor. We applied 5-fold cross-validation and used the validation set to evaluate the classification performance of the artificial neural network models.

Results

Overall, 2,240 patients were enrolled in this study. The median length of hospital stay was 9 days. A total of 1,101 patients (49.2%) had a prolonged hospital stay. A prolonged length of stay is associated with worse neurological outcomes at discharge. Univariate analysis identified 14 baseline parameters associated with prolonged length of stay, and with these parameters as input, the artificial neural network model achieved training and validation areas under the curve of 0.808 and 0.788, respectively. The mean accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of prediction models were 74.5, 74.9, 74.2, 75.2, and 73.9%, respectively. The key factors associated with prolonged length of stay were National Institutes of Health Stroke Scale scores at admission, atrial fibrillation, receiving thrombolytic therapy, history of hypertension, diabetes, and previous stroke.

Conclusion

The artificial neural network model achieved adequate discriminative power for predicting prolonged length of stay after acute ischemic stroke and identified crucial factors associated with a prolonged hospital stay. The proposed model can assist in clinically assessing the risk of prolonged hospitalization, informing decision-making, and developing individualized medical care plans for patients with acute ischemic stroke.

Stroke mortality prediction using machine learning: systematic review

BACKGROUND AND AIMS

Accurate prognostication of stroke may help in appropriate therapy and rehabilitation planning. In the past few years, several machine learning (ML) algorithms were applied for prediction of stroke outcomes. We aimed to examine the performance of machine learning-based models for the prediction of mortality after stroke, as well as to identify the most prominent factors for mortality.

MATERIALS AND METHODS

We searched MEDLINE/PubMed and Web of Science databases for original publications on machine learning applications in stroke mortality prediction, published between January 1, 2011, and October 27, 2022. Risk of bias and applicability were evaluated using the tailored QUADAS-2 tool.

RESULTS

Of the 1015 studies retrieved, 28 studies were included. Twenty-Five studies were retrospective. The ML models demonstrated a favorable range of AUC for mortality prediction (0.67-0.98). In most of the articles, the models were applied for short-term post stroke mortality. The number of explanatory features used in the models to predict mortality ranged from 5 to 200, with substantial overlap in the variables included. Age, high BMI and high NIHSS score were identified as important predictors for mortality. Almost all studies had a high risk of bias in at least one category and concerns regarding applicability.

CONCLUSION

Using machine learning, data available at the time of admission may aid in stroke mortality prediction. Notwithstanding, current research is based on few preliminary works with high risk of bias and high heterogeneity. Thus, future prospective, multicenter studies with standardized reports are crucial to firmly establish the usefulness of the algorithms in stroke prognostication.

Subgroup State Prediction under Different Noise Levels Using MODWT and XGBoost

In medical states prediction, the observations of different individuals are generally assumed to follow an identical distribution, whereas precision medicine has a rigorous requirement for accurate subgroup analysis. In this research, an aggregated method is proposed by means of combining the results generated from different subgroup models and is compared with the original method for different denoising levels as well as the prediction gaps. The results using real data demonstrate the effectiveness of the aggregated method exhibiting superior performance such as 0.95 in AUC, 0.87 in F1, and 0.82 in sensitivity, particularly for the denoising level that is set to be 2. With respect to the variable importance, it is shown that some variables such as heart rate and lactate arterial become more important when the denoising level increases.

Data-driven methodology to predict the ICU length of stay: A multicentre study of 99,492 admissions in 109 Brazilian units

PURPOSE

The length of stay (LoS) is one of the most used metrics for resource use in Intensive Care Units (ICU). We propose a structured data-driven methodology to predict the ICU length of stay and the risk of prolonged stay, and its application in a large multicenter Brazilian ICU database.

METHODS

Demographic data, comorbidities, complications, laboratory data, and primary and secondary diagnosis were prospectively collected and retrospectively analysed by a data-driven methodology, which includes eight different machine learning models and a stacking model. The study setting included 109 mixed-type ICUs from 38 Brazilian hospitals and the external validation was performed by 93 medical-surgical ICUs of 55 hospitals in Brazil.

RESULTS

A cohort of 99,492 adult ICU admissions were included from the 01^st of January to the 31^st of December 2019. The stacking model combining Random Forests and Linear Regression presented the best results to predict ICU length of stay (RMSE = 3.82; MAE = 2.52; R² = 0.36). The prediction model for the risk of long stay were accurate to early identify prolonged stay patients (Brier Score = 0.04, AUC = 0.87, PPV = 0.83, NPV = 0.95).

CONCLUSION

The data-driven methodology to predict ICU length of stay and the risk of long-stay proved accurate in a large multicentre cohort of general ICU patients. The proposed models are helpful to predict the individual length of stay and to early identify patients with high risk of prolonged stay.

Determinants of Prolonged Length of Hospital Stay in Patients with Severe Acute Ischemic Stroke

OBJECTIVE

Long hospitalizations are associated with a high comorbidity and considerable hospital cost. Admissions of severe acute ischemic stroke are prone to longer hospitalizations. We aimed to explore the issue and method for improving the length of stay.

METHODS

From the prospective Stroke Registry between January 2019 and June 2020, acute ischemic strokes with an admission National Institutes of Health Stroke Scale ≥ 15 were identified. Prolonged length-of-stay was defined as in-hospital-stay ≥ 30 days. All clinical characteristics were collected, and all do-not-resuscitate documentations were categorized if the order had been written within 7 days of onset.

RESULTS

A total of 212 patients were eligible for severe stroke. Of these, 42 (19.8%) had prolonged length-of-stay and 170 had non-prolonged length-of-stay (median 43 vs. 13 days). The prolonged group was younger, mostly men, and was more likely to be in an independent state and more likely to receive reperfusion therapy, and there was a higher frequency of late do-not-resuscitate orders if signed. Although there was a lower in-hospital mortality rate in the prolonged group (12% vs. 23%), there was a higher proportion with a severe functional state (Modified Rankin Scale = 4-5) among the survivors (97% vs. 87%).

CONCLUSIONS

Severe acute ischemic stroke patients with a prolonged length-of-stay were younger, mostly male, more likely to receive reperfusion therapy, less likely to have an early do-not-resuscitate order if signed, and more likely to have poor functional status at discharge, although there was a lower rate of in-hospital mortality.